Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4579 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.5561. Min Act: -0.0000

Data Index: 362247 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.4219. Min Act: -0.0000

Data Index: 38889 (The Pile)

Max Activating Token Index: 243

Text #2

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.3201. Min Act: -0.0000

Data Index: 455991 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.1284. Min Act: -0.0000

Data Index: 232122 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1072788 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.1822. Min Act: -0.0000

Data Index: 697987 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.1912. Min Act: -0.0000

Data Index: 1641251 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.0912. Min Act: -0.0000

Data Index: 1899577 (The Pile)

Max Activating Token Index: 43

Text #8

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1289918 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1068425 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.2301. Min Act: -0.0000

Data Index: 1207218 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 1.5561. Min Range: -1.5561

Max Act: 0.9742. Min Act: -0.0000

Data Index: 130994 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.0607. Min Act: -0.0000

Data Index: 771202 (The Pile)

Max Activating Token Index: 441

Text #13

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.0215. Min Act: -0.0000

Data Index: 649230 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 1.5561. Min Range: -1.5561

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1320259 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 1.5561. Min Range: -1.5561

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1538373 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 1.5561. Min Range: -1.5561

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1872682 (The Pile)

Max Activating Token Index: 807

Text #17

Max Range: 1.5561. Min Range: -1.5561

Max Act: 0.9882. Min Act: -0.0000

Data Index: 258980 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 1.5561. Min Range: -1.5561

Max Act: 0.9424. Min Act: -0.0000

Data Index: 866529 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 1.5561. Min Range: -1.5561

Max Act: 0.9695. Min Act: -0.0000

Data Index: 273593 (The Pile)

Max Activating Token Index: 392